• Purva Nagrale
• Khushi Gangrade
• Siddhi Pasalkar
• Sakshi Purvant

In the world of meteorological forecasting and atmospheric analysis, the integration of deep learning techniques has ushered in a transformative era, particularly in the analysis of satellite images. This study focuses on leveraging cutting-edge neural network architectures, such as Convolutional Neural Networks (CNNs), to extract intricate patterns, spectral data, and spatial features from satellite imagery. The primary goal is to facilitate precise estimation and forecasting of various weather parameters, including cloud cover, precipitation, and temperature fluctuations. The proposed system follows a systematic approach, encompassing phases such as image uploading, pre-processing, image processing, feature extraction, classification, similarity measurement, and weather prediction. Utilizing the Waterfall Model in the Software Development Life Cycle (SDLC), the project emphasizes rigorous testing, deployment, and maintenance for robust and reliable performance.

Deep Learning, Convolutional Neural Networks (CNNs), Satellite Image Analysis, Meteorological Forecasting, Classification Algorithms, Similarity Measurement

"Weather Nova: Deep Learning-powered Image Retrieval for Weather Analysis", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 1, page no.g1-g8, January-2024, Available :http://www.jetir.org/papers/JETIR2401601.pdf

"Weather Nova: Deep Learning-powered Image Retrieval for Weather Analysis", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 1, page no. ppg1-g8, January-2024, Available at : http://www.jetir.org/papers/JETIR2401601.pdf